Upload config.json with huggingface_hub
Browse files- config.json +113 -0
config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "hibiki",
|
| 3 |
+
"lmgen_config": {
|
| 4 |
+
"temp": 0.8,
|
| 5 |
+
"text_temp": 0.8,
|
| 6 |
+
"top_k": 250,
|
| 7 |
+
"text_top_k": 50
|
| 8 |
+
},
|
| 9 |
+
"dim": 2560,
|
| 10 |
+
"text_card": 48000,
|
| 11 |
+
"existing_text_padding_id": 3,
|
| 12 |
+
"n_q": 32,
|
| 13 |
+
"dep_q": 16,
|
| 14 |
+
"card": 2048,
|
| 15 |
+
"num_heads": 20,
|
| 16 |
+
"num_layers": 24,
|
| 17 |
+
"hidden_scale": 4.125,
|
| 18 |
+
"causal": true,
|
| 19 |
+
"layer_scale": null,
|
| 20 |
+
"context": 500,
|
| 21 |
+
"max_period": 100000,
|
| 22 |
+
"gating": "silu",
|
| 23 |
+
"norm": "rms_norm_f32",
|
| 24 |
+
"positional_embedding": "rope",
|
| 25 |
+
"depformer_dim": 1024,
|
| 26 |
+
"depformer_dim_feedforward": 3072,
|
| 27 |
+
"depformer_num_heads": 16,
|
| 28 |
+
"depformer_num_layers": 4,
|
| 29 |
+
"depformer_causal": true,
|
| 30 |
+
"depformer_layer_scale": null,
|
| 31 |
+
"depformer_multi_linear": true,
|
| 32 |
+
"depformer_context": 16,
|
| 33 |
+
"depformer_max_period": 10000,
|
| 34 |
+
"depformer_gating": "silu",
|
| 35 |
+
"depformer_pos_emb": "none",
|
| 36 |
+
"depformer_weights_per_step": true,
|
| 37 |
+
"depformer_weights_per_step_schedule": [
|
| 38 |
+
0,
|
| 39 |
+
1,
|
| 40 |
+
2,
|
| 41 |
+
3,
|
| 42 |
+
4,
|
| 43 |
+
5,
|
| 44 |
+
6,
|
| 45 |
+
7,
|
| 46 |
+
8,
|
| 47 |
+
8,
|
| 48 |
+
8,
|
| 49 |
+
8,
|
| 50 |
+
8,
|
| 51 |
+
8,
|
| 52 |
+
8,
|
| 53 |
+
8
|
| 54 |
+
],
|
| 55 |
+
"depformer_low_rank_embeddings": 128,
|
| 56 |
+
"delays": [
|
| 57 |
+
0,
|
| 58 |
+
0,
|
| 59 |
+
2,
|
| 60 |
+
2,
|
| 61 |
+
2,
|
| 62 |
+
2,
|
| 63 |
+
2,
|
| 64 |
+
2,
|
| 65 |
+
2,
|
| 66 |
+
2,
|
| 67 |
+
2,
|
| 68 |
+
2,
|
| 69 |
+
2,
|
| 70 |
+
2,
|
| 71 |
+
2,
|
| 72 |
+
2,
|
| 73 |
+
2,
|
| 74 |
+
0,
|
| 75 |
+
2,
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
2,
|
| 79 |
+
2,
|
| 80 |
+
2,
|
| 81 |
+
2,
|
| 82 |
+
2,
|
| 83 |
+
2,
|
| 84 |
+
2,
|
| 85 |
+
2,
|
| 86 |
+
2,
|
| 87 |
+
2,
|
| 88 |
+
2,
|
| 89 |
+
2
|
| 90 |
+
],
|
| 91 |
+
"conditioners": {
|
| 92 |
+
"description": {
|
| 93 |
+
"type": "lut",
|
| 94 |
+
"lut": {
|
| 95 |
+
"n_bins": 31,
|
| 96 |
+
"dim": 16,
|
| 97 |
+
"tokenizer": "noop",
|
| 98 |
+
"possible_values": [
|
| 99 |
+
"very_bad",
|
| 100 |
+
"bad",
|
| 101 |
+
"neutral",
|
| 102 |
+
"good",
|
| 103 |
+
"very_good"
|
| 104 |
+
]
|
| 105 |
+
}
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"fuser": {
|
| 109 |
+
"sum": [
|
| 110 |
+
"description"
|
| 111 |
+
]
|
| 112 |
+
}
|
| 113 |
+
}
|